Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3599 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0317. Min Range: -3.0317

Max Act: 3.0317. Min Act: -0.0001

Data Index: 1093858 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.5049. Min Act: -0.0000

Data Index: 962832 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.4810. Min Act: -0.0000

Data Index: 58375 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.4059. Min Act: -0.0001

Data Index: 1133399 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.1589. Min Act: -0.0000

Data Index: 540666 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.2602. Min Act: -0.0001

Data Index: 404793 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.1478. Min Act: -0.0001

Data Index: 908888 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.1526. Min Act: -0.0001

Data Index: 685073 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.1411. Min Act: -0.0001

Data Index: 411405 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 3.0317. Min Range: -3.0317

Max Act: 1.9164. Min Act: -0.0001

Data Index: 675414 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.0415. Min Act: -0.0001

Data Index: 614590 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.0302. Min Act: -0.0001

Data Index: 889689 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.0270. Min Act: -0.0000

Data Index: 1246372 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.0237. Min Act: -0.0000

Data Index: 1143522 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 3.0317. Min Range: -3.0317

Max Act: 1.8895. Min Act: -0.0000

Data Index: 249048 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.0703. Min Act: -0.0001

Data Index: 725673 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.0555. Min Act: -0.0001

Data Index: 592154 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.0489. Min Act: -0.0001

Data Index: 52061 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 3.0317. Min Range: -3.0317

Max Act: 1.9305. Min Act: -0.0000

Data Index: 976021 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 3.0317. Min Range: -3.0317

Max Act: 1.8241. Min Act: -0.0001

Data Index: 229276 (C4 (Web Text))

Max Activating Token Index: 739